Solace Message Routers and Cisco Ethernet Switches: Unified Infrastructure for Financial Services Middleware
|
|
- Brett Lawrence
- 5 years ago
- Views:
Transcription
1 Solace Message Routers and Cisco Ethernet Switches: Unified Infrastructure for Financial Services Middleware What You Will Learn The goal of zero latency in financial services has caused the creation of entirely new industries, products, and career paths as well as volumes of data, analysis, and opinion. The degree to which speed in market-data delivery, trading algorithms, and transactions influences profit cannot be overemphasized and is the motivation behind many financial firms obsession with low latency. Every aspect of the data path, from messaging platform architecture to networking infrastructure, is being reviewed carefully in an attempt to gain competitive advantage. Many IT departments have approached the task by disaggregating the elements and testing them in isolation with simple synthetic tests that vary dramatically from the production requirements. However, it is important that missioncritical systems be tested in combination with as many real-world behaviors as possible to understand how factors like network load, variable message size, and spikes in volume affect latency and jitter. This document introduces the architecture and performance of an end-to-end middleware solution based on Solace message routers and Cisco networking equipment. This all-hardware solution enables customers to deploy and manage middleware environments that support the ultra-low latency and high message rates they need with much lower cost and complexity than systems that introduce software into the equation. The tests show consistent low latency, even with bursty traffic, variable message sizes, and high message volumes. This document discusses a comprehensive set of tests, but Table 1 shows an example of the results measured from publisher to subscriber using a Cisco Catalyst 4900M Switch and a Solace 3260 Message Router. Table 1. Sample Test Results Using a Cisco Catalyst 4900M Switch and a Solace 3260 Message Router Configuration 1a Message Pattern 1 Message Pattern 2 Average Latency 31 microseconds 33 microseconds 99 th Percentile Latency 47 microseconds 51 microseconds Standard Deviation 3.1 microseconds 3.8 microseconds * Message Pattern 1 = 500,000 messages per second (msg/sec) continuous + 500,000 msg/sec bursts * Message Pattern 2 = 1 million msg/sec continuous + 500,000 msg/sec bursts Defining the Low-Latency Systems of Tomorrow Delivering Ultra-Low Latency A wide array of options is available to financial services companies that are seeking to be first to market with trading ideas or trade execution. Historically, end-to-end market-data latency was often 100 microseconds or more, with most of that latency in the applications and messaging layers, and with the network representing a very small percentage. Consequently, any above the network logic that can be optimized in hardware or consolidated to reduce transport latency has the potential to deliver the most significant performance improvements. Solace s unique approach uses field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), and network processors to perform critical messaging and message processing in hardware and enables ultra-low, consistent latency, even at high volumes Cisco Systems, Inc. All rights reserved. This document is Cisco Public Information. Page 1 of 15
2 At the same time, many networking engineers and architects correctly observe that as improvements are achieved for messaging, the percentage of latency attributable to the network increases. With many algorithmic trading strategies, success or loss can be measured in microseconds, causing architects to aim for low end-to-end latency. Just as important is low variability of latency, or jitter. Cisco s Ethernet switches deliver the low latency at both Layers 2 and 3, allowing clients to select the architectures that best meet their business requirements. Moreover, the design of the switch includes custom ASICs that provide deep buffers that allow the switch to accommodate the inevitable bursty traffic encountered in trading and market-data environments. The testing in this document demonstrates how the Cisco Catalyst 4900M Switch and the Cisco Nexus 5010 Switch reduce retransmissions and thus keep latency low and steady. Choosing network equipment with higher retransmission rates can have catastrophic consequences for application performance and risks noncompliance with regulatory requirements for fairness. Unfortunately, many teams that build low-latency systems find that components that tested well in isolation using synthetic traffic patterns may deliver less optimal or less predictable results when stressed by periods of market volatility, when they are most needed. Market-data test methodologies are so well understood by the industry that some vendors would appear to have optimized their products for test suites rather than real-world circumstances. It is essential to evaluate the components both in isolation and when working together as a system to help ensure the best competitive advantage in the end system. In the test results that follow, Solace and Cisco equipment demonstrates market-leading performance using a range of tests that simulate real-world conditions such as mixed message sizes and bursty market-data rates. Enabling Consolidation CIOs must find ways to do more with less without sacrificing their ability to quickly scale and shift direction, and the best way to reduce architectural complexity and total cost of ownership (TCO) is by consolidating multiple technologies onto a single platform. For middleware, consolidation has not been possible until now because no one technology could satisfy all middleware needs or provide the performance and scalability needed to support enterprise deployments. Solace s Unified Messaging Platform consolidates all messaging functions into a single appliance with a common API and shared administration environment. Solace s hardware-based middleware can perform high-fanout, low-latency, guaranteed, Java Message Service (JMS) and WAN messaging, as well as content-based routing, transformation, and message caching. As a hardware-based platform, Solace s solution delivers exceptional performance and resilience with low cost of ownership. For networking equipment, the expansion of capacity from 100 Mbps to 1 Gbps and now 10 Gbps enables a greater variety and volume of data to flow through a given device or data center. Cisco supports consolidation in this arena with the Cisco Catalyst and Cisco Nexus switches, which have been designed for the data center and deliver low, consistent latency even when carrying many different kinds of traffic. By using the intelligence of the network for context and collaboration, organizations can move with greater speed and agility. Enabling Intelligent Architecture One downside of running multiple purpose-specific networks and messaging systems is that financial institutions have had to sacrifice good network design principles to achieve the lowest possible latency. The combination of Solace message routers and Cisco switches enables a clean, scalable network design that consists of Layer 2 and 3 where appropriate while enabling extremely low, predictable latency Cisco Systems, Inc. All rights reserved. This document is Cisco Public Information. Page 2 of 15
3 Whether Solace s message routers are given their own data center subnet or share a subnet with other assets such as file servers, each department (equities, fixed income, finance, etc.) can have its own subnet for network connectivity without sacrificing messaging performance. This feature makes it easy to isolate traffic at the IP and messaging layers while gaining the advantages of a common infrastructure: simpler deployment and administration, greater visibility and control, and lower TCO. Such a system supports the connection of local and remote sites, along with the existence of a mixture of 10-Gbps, 1-Gbps, and 100-Mbps host interface speeds. The solution does not require any custom tuning of the network to achieve optimum performance, is highly scalable, and follows good network design principles. High-Performance Market-Data Delivery Using TCP Unicast Solace s message routers deliver information using unicast over client-specific TCP connections instead of multicast. Thus, subscriber-specific filtration is performed in the Solace message router as part of the delivery process, so clients are sent only the information they need. Bandwidth is not wasted on the delivery of unwanted messages, clients do not waste CPU cycles filtering and discarding unwanted messages, and interrupt coalescing can be turned off because clients can handle the inbound rate of this custom prefiltered data feed. Solace s routing protocols are optimized for this unicast delivery, enabling highly efficient data distribution over both LANs and WANs. The use of TCP-based unicast also eliminates the hassle of administering multicast groups, the risk of high volumes of negative-acknowledgment traffic, and the potentially debilitating ripple effects of slow or misbehaving clients. It also provides granular visibility with client-specific metrics that let administrators address performance problems with speed and certainty. (For more information, please read this document at Solace s website.) Proving the Power of Cisco and Solace To demonstrate the advantages of building a front-to-back financial services infrastructure using a combination of Cisco and Solace hardware, Cisco and Solace developed a reference architecture and ran a series of tests designed to represent a real-world scenario that is characterized by high message volume, mixed message sizes, and the kind of variability that characterizes periods of market volatility. The architecture and test traffic simulates a high-frequency trading environment, with market data coming in from a variety of feeds, being distributed to algorithmic trading engines, and ultimately being sent to several mid- and backoffice systems for risk analysis and trade execution. To approximate real-world message and network traffic, the tests included a high degree of variability in many dimensions. All tests used mixed messages sizes to simulate a single consolidated information bus on a shared network infrastructure. All tests described in this document generated 67 percent market-data volume (100 bytes) and 33 percent mid- and back-office volume (600 bytes). Traffic volume was varied with the addition of 1-second bursts of additional data every other second (Figure 1) Cisco Systems, Inc. All rights reserved. This document is Cisco Public Information. Page 3 of 15
4 Figure 1. Reference Architecture System Architecture and Test Scenarios Figure 2 shows the architecture, components, and physical topology of the test system. The test system uses four configurations spanning a primary network and a secondary network. In these tests, a Cisco Catalyst switch in the primary network has direct connections to the Solace message router, and back-office servers and other departments are on separate subnets. Each of the primary and secondary networks has two separate test configurations (a and b), as shown in the figures and detailed in the results section of this document Cisco Systems, Inc. All rights reserved. This document is Cisco Public Information. Page 4 of 15
5 Figure 2. Test System Architecture, Components, and Topology Shared Messaging Infrastructure All applications shared a messaging backbone located in the primary network. In scenario 1a, the Solace message router was directly connected to a Cisco Catalyst 4900M low-latency switch. In scenario 1b, the feed and algorithm are connected to a Cisco Nexus 5000 Series Switch, which routes traffic at Layer 2 to the Cisco Catalyst 4900M in the same network. In the secondary network, clients and servers were connected to their own Cisco 4900M switches, which used Layer 3 routing to direct traffic to the primary network and in turn to the Solace message router. In these tests, a single Solace message router is shared for message routing in both networks. This design is commonly selected because it produces all the performance improvements of hardware messaging while reducing costs by reusing routers across applications and message types. For extremely latency-sensitive applications, customers have the option of placing additional Solace message routers in the secondary network to reduce network hops and increase performance Cisco Systems, Inc. All rights reserved. This document is Cisco Public Information. Page 5 of 15
6 Bursty Traffic In each configuration, two message pattern tests were run that have baseline volumes of 500,000 and 1 million messages per second with bursts of an additional 500,000 messages every other second: that is, in the first test the volume oscillated between 500,000 and 1 million messages per second each second, and in the second test the volume oscillated between 1 million and 1.5 million messages per second each second (Figure 3). Figure 3. Message Patterns Mixed Message Sizes All tests were designed to show how one consolidated infrastructure could meet the needs of front-, middle-, and back-office traffic. For each test, two-thirds of the messages were 100 bytes in size to simulate market-data messages, and the other third were 600 bytes in size to simulate middle- or back-office traffic such as orders, risk management updates, and compliance messages (Figure 4). Figure 4. Mixed Message Sizes All messages were sent individually using reliable messaging. In reality, some of the middle- and back-office messages would be sent using guaranteed messaging. The same Solace equipment that was used in this test can also route 135,000 guaranteed messages per second without affecting reliable messaging throughput or latency Cisco Systems, Inc. All rights reserved. This document is Cisco Public Information. Page 6 of 15
7 API-to-API Measurements All latency measurement was performed from the messaging API on the feed to the messaging API on the algorithmic engine (Figure 5). This approach provides a more realistic representation of performance than measuring just wire-to-wire latency or time through only the messaging bus. All results include everything you should expect in a production deployment of a Solace messaging backbone and Cisco network. Figure 5. API-to-API Measurements Test Environment and Scenarios Figure 6 shows the logical topology of the network, including a breakdown of subnets. The red arrows signify the flow of market-data messages (100 bytes) between each feed and algorithm pair, and the green arrows show traffic from the algorithms to the back-office applications (600 bytes) Cisco Systems, Inc. All rights reserved. This document is Cisco Public Information. Page 7 of 15
8 Figure 6. Logical Network Topology Two traffic volumes were tested, and latency was measured for three configurations. The first test used steady traffic of 500,000 messages per second, with 1-second bursts of an additional 500,000 messages per second every other second. The second test was run with steady traffic of 1 million messages per second, with 1-second bursts of an additional 500,000 messages every other second. In both tests, two-thirds of the traffic consisted of 100-byte messages to simulate market data, and the other third were 600 bytes to simulate back-office traffic such as orders being sent for execution or risk assessment. Most client applications used kernel bypass (KB in the figures) technology to accelerate TCP processing on the hosts. Kernel bypass is a technique that can be used in conjunction with either a TCP offload engine or a specialpurpose network interface card (NIC) to eliminate operating system delays, resulting in improved TCP performance at high volumes. For comparison, test 2b shows the performance of a standard software TCP stack with a standard NIC and no kernel bypass Cisco Systems, Inc. All rights reserved. This document is Cisco Public Information. Page 8 of 15
9 Results of Configuration 1a In the first configuration (Figure 7), feed 1a, algorithmic engine 1a, and the Solace 3260 Message Router were directly connected to the same Cisco Catalyst 4900M Switch using Layer 2 switching for all traffic. The feed and algorithmic engine servers used TCP kernel bypass technology installed to accelerate network processing at the application hosts. This configuration, with the message router directly connected to the switch, represents the most common approach to achieving the lowest possible latency since the number of network hops is reduced and hardware middleware is keeping the latency of high-volume traffic low and predictable. Figure 7. Configuration 1a Note that in message pattern 2, despite a 50 percent increase in the message volume and network load, average latency increased only 2 microseconds, and standard deviation increased only 700 nanoseconds. With 67 percent of the messages being 100 bytes in size and 33 percent being 600 bytes in size, message pattern 2 was peaking above 3.2 Gbps of throughput. This is not close to the limits of the network or messaging equipment, but is a significant load. One million market-data messages plus 500,000 back-office events per second exceeds most trading room capabilities today, and the test results demonstrate much lower latency and standard deviation than would be expected in most currently deployed systems (Table 2). Table 2. Results of Test 1a Configuration 1a Message Pattern 1 Message Pattern 2 Average Latency 31 microseconds 33 microseconds 99 th Percentile Latency 47 microseconds 51 microseconds Standard Deviation 3.1 microseconds 3.8 microseconds * Message Pattern 1 = 500,000 msg/sec continuous + 500,000 msg/sec bursts * Message Pattern 2 = 1 million msg/sec continuous + 500,000 msg/sec bursts Results of Configuration 1b: Layer 2 with Cisco Nexus Switch The second configuration Figure 8) introduces a Cisco Nexus 5000 Series Switch, providing additional 10 Gigabit Ethernet ports to the primary network. Feed 1b and algorithm 1b are connected to the Solace message router through the Cisco Nexus 5000 Series Switch and the Cisco Catalyst 4900M Switch entirely using Layer 2. Both the feed and algorithm devices are using kernel bypass, as was true in configuration 1a Cisco Systems, Inc. All rights reserved. This document is Cisco Public Information. Page 9 of 15
10 Figure 8. Configuration 1b The results show a modest increase in absolute latency and little effect on jitter despite the introduction of a second switch and the high volumes tested (Table 3). Table 3. Results of Test 1b Configuration 1b Message Pattern 1 Message Pattern 2 Average Latency 37 microseconds 40 microseconds 99 th Percentile Latency 54 microseconds 57 microseconds Standard Deviation 3.4 microseconds 3.9 microseconds * Message Pattern 1 = 500,000 msg/sec continuous + 500,000 msg/sec bursts * Message Pattern 2 = 1 million msg/sec continuous + 500,000 msg/sec bursts Results of Configuration 2a: Layer 3 with Kernel Bypass The third configuration (Figure 9) is the first of two in the secondary network. Feed 2a and algorithm 2a are connected to the Solace message router through the Cisco Catalyst 4900M Switches in the secondary and primary networks using Layer 3 routing. Both the feed and algorithm devices use kernel bypass, as in the first two configurations. The difference is that the Cisco router in configuration 2a connects using Layer 3, whereas the Cisco switch in configurations 1a and 1b was connected using Layer Cisco Systems, Inc. All rights reserved. This document is Cisco Public Information. Page 10 of 15
11 Figure 9. Configuration 2a The results show no significant performance difference between Layer 2 and Layer 3 connectivity in terms of latency or messaging volume (Table 4). Table 4. Results of Test 2a Configuration 2a Message Pattern 1 Message Pattern 2 Average Latency 37 microseconds 40 microseconds 99 th Percentile Latency 54 microseconds 57 microseconds Standard Deviation 3.4 microseconds 3.9 microseconds * Message Pattern 1 = 500,000 msg/sec continuous + 500,000 msg/sec bursts * Message Pattern 2 = 1 million msg/sec continuous + 500,000 msg/sec bursts 2010 Cisco Systems, Inc. All rights reserved. This document is Cisco Public Information. Page 11 of 15
12 Results of Configuration 2b: Layer 3 with NIC The fourth configuration (Figure 10), using feed and algorithm pair 2b, is identical to configuration 2a except that the feed and algorithmic devices were configured without client-side TCP acceleration. The NIC is still a 10 Gigabit Ethernet interface card, but the TCP stack is running in software with normal OS kernel interactions. Figure 10. Configuration 2b 2010 Cisco Systems, Inc. All rights reserved. This document is Cisco Public Information. Page 12 of 15
13 The results show that running kernel bypass technology in test 2a reduced latency by 16 to 17 microseconds compared to the results in test 2b (Table 5). Table 5. Results of Test 2b Configuration 2b Message Pattern 1 Message Pattern 2 Average Latency 54 microseconds 56 microseconds 99 th Percentile Latency 71 microseconds 71 microseconds Standard Deviation 6.5 microseconds 6.2 microseconds * Message Pattern 1 = 500,000 msg/sec continuous + 500,000 msg/sec bursts * Message Pattern 2 = 1 million msg/sec continuous + 500,000 msg/sec bursts Conclusion These test results demonstrate that an architecture consisting of hardware Solace message routers and Cisco switches deliver system latency and throughput that exceeds the requirements of the most demanding latencysensitive financial services environments. This combination delivered consistently low latency and low jitter through both Layers 2 and 3 connectivity, even with bursty traffic, variable message sizes, and high message rates. Further reductions can be achieved using kernel bypass for TCP acceleration on the client application machines. Testing with traffic patterns that mimic real-world environments at times of market volatility helps ensure that the system will function in the production environment with the same performance characteristics that are documented in the evaluation environment. For More Information For more information, please contact your Cisco or Solace salesperson to find out how this solution can help you improve the performance of your systems with remarkably low TCO Cisco Systems, Inc. All rights reserved. This document is Cisco Public Information. Page 13 of 15
14 Appendix: Performance of a Direct Cisco Nexus 5000 Series Connection For completeness, configuration 1a described earlier in this document was separately run with a Cisco Nexus 5000 Series Switch in place of the Cisco Catalyst 4900M as the device directly connected to all other test components. System Architecture and Test Scenario Figure 11 shows the logical topology of the network. The feed, algorithmic engine, back-office applications, and Solace 3260 Message Router were directly connected to the Cisco Nexus 5000 Series router using Layer 2 switching for all traffic. The application servers used TCP kernel bypass technology to accelerate TCP processing at the application hosts. Figure 11. Configuration Using Cisco Nexus 5000 Series The system was tested with the same parameters as those described earlier in this document. Two traffic volumes were tested: steady traffic of 500,000 messages per second, with 1-second bursts of an additional 500,000 messages per second every other second, and steady traffic of 1 million messages per second, with bursts of an additional 500,000 messages. In both tests, two-thirds of the traffic consisted of 100-byte messages to simulate market data, and the other third were 600 bytes to simulate back-office traffic such as orders being sent for execution or risk assessment. All client applications used kernel bypass technology to accelerate TCP processing. Kernel bypass is a technique that can be used in conjunction with either a TCP offload engine or a special-purpose NIC to eliminate OS interrupts, resulting in improved TCP performance at high volume. Results The system exhibited remarkably low latency, averaging 32 microseconds in message pattern 1 and 34 microseconds in message pattern 2. Note that despite a 50 percent increase in throughput, average latency increased just 2 microseconds, and standard deviation increased a mere 700 nanoseconds. With 67 percent of the messages being 100 bytes in size, and 33 percent being 600 bytes in size, test 2 was peaking above 3.2 Gbps throughput, which is not near the limits of the network or messaging equipment, but a significant load. One million market-data messages plus 500,000 risk, trade, and other mid-back office events per second exceeds most trading room capabilities today, with much lower latency and standard deviation (Table 6) Cisco Systems, Inc. All rights reserved. This document is Cisco Public Information. Page 14 of 15
15 Table 6. Results of Test Using Cisco Nexus 5000 Series Configuration Using Cisco Nexus 5000 Series Message Pattern 1 Message Pattern 2 Average Latency 32 microseconds 34 microseconds 99 th Percentile Latency 49 microseconds 52 microseconds Standard Deviation 3.4 microseconds 3.8 microseconds * Message Pattern 1 = 500,000 msg/sec continuous + 500,000 msg/sec bursts * Message Pattern 2 = 1 million msg/sec continuous + 500,000 msg/sec bursts Conclusion These results show that an architecture consisting of Solace message routers and Cisco Nexus switches delivers latency and throughput that exceed the requirements of the most latency-sensitive financial services environments. This combination delivers consistently low latency and low jitter through, even with bursty traffic, variable message sizes, and high message rates. Printed in USA C / Cisco Systems, Inc. All rights reserved. This document is Cisco Public Information. Page 15 of 15
Cisco Nexus 6004 Switch Performance Validation
Cisco Nexus 6004 Switch Performance Validation White Paper February 2013 2013 Cisco Ixia. All rights reserved. Page 1 Contents What You Will Learn... 3 Overview... 3 Test Bed... 4 How Testing Was Performed...
More informationSolace JMS Broker Delivers Highest Throughput for Persistent and Non-Persistent Delivery
Solace JMS Broker Delivers Highest Throughput for Persistent and Non-Persistent Delivery Java Message Service (JMS) is a standardized messaging interface that has become a pervasive part of the IT landscape
More informationCisco Wide Area Application Services and Cisco Nexus Family Switches: Enable the Intelligent Data Center
Cisco Wide Area Application Services and Cisco Nexus Family Switches: Enable the Intelligent Data Center What You Will Learn IT departments are facing increasing pressure to accommodate numerous changing
More informationMODERNIZE YOUR DATA CENTER. With Cisco Nexus Switches
MODERNIZE YOUR DATA CENTER With Cisco Nexus Switches TABLE OF CONTENTS TABLE OF CONTENTS Data Center Needs are Changing Cisco Nexus Switches Lead the Transition to a Next Generation Data Center Outcomes
More informationUSING ISCSI AND VERITAS BACKUP EXEC 9.0 FOR WINDOWS SERVERS BENEFITS AND TEST CONFIGURATION
WHITE PAPER Maximize Storage Networks with iscsi USING ISCSI AND VERITAS BACKUP EXEC 9.0 FOR WINDOWS SERVERS BENEFITS AND TEST CONFIGURATION For use with Windows 2000 VERITAS Software Corporation 03/05/2003
More informationCisco Unified Computing System Delivering on Cisco's Unified Computing Vision
Cisco Unified Computing System Delivering on Cisco's Unified Computing Vision At-A-Glance Unified Computing Realized Today, IT organizations assemble their data center environments from individual components.
More informationLab Test Report DR100401D. Cisco Nexus 5010 and Arista 7124S
Lab Test Report DR100401D Cisco Nexus 5010 and Arista 7124S 1 April 2010 Miercom www.miercom.com Contents Executive Summary... 3 Overview...4 Key Findings... 5 How We Did It... 7 Figure 1: Traffic Generator...
More informationIBM Europe Announcement ZP , dated November 6, 2007
IBM Europe Announcement ZP07-0484, dated November 6, 2007 IBM WebSphere Front Office for Financial Markets V2.0 and IBM WebSphere MQ Low Latency Messaging V2.0 deliver high speed and high throughput market
More informationCisco Nexus 3548 Switch Performance Validation December 2012
Cisco Nexus 3548 Switch Performance Validation December 212 212 Spirent Cisco. All rights reserved. Page 1 Contents Executive Summary... 3 Test Bed... 4 How Testing Was Performed... 4 Test Results... 6
More informationCisco SAN Analytics and SAN Telemetry Streaming
Cisco SAN Analytics and SAN Telemetry Streaming A deeper look at enterprise storage infrastructure The enterprise storage industry is going through a historic transformation. On one end, deep adoption
More informationThe QLogic 8200 Series is the Adapter of Choice for Converged Data Centers
The QLogic 82 Series is the Adapter of QLogic 1GbE Converged Network Adapter Outperforms Alternatives in Dell 12G Servers QLogic 82 Series Converged Network Adapter outperforms the alternative adapter
More informationEqualLogic Storage and Non-Stacking Switches. Sizing and Configuration
EqualLogic Storage and Non-Stacking Switches Sizing and Configuration THIS WHITE PAPER IS FOR INFORMATIONAL PURPOSES ONLY, AND MAY CONTAIN TYPOGRAPHICAL ERRORS AND TECHNICAL INACCURACIES. THE CONTENT IS
More informationEthernet Wide Area Networking, Routers or Switches and Making the Right Choice
Ethernet Wide Area Networking, Routers or Switches and Making the Right Choice The Road To Ethernet WAN Various industry sources show trends in globalization and distribution, of employees moving towards
More informationUsing Switches with a PS Series Group
Cisco Catalyst 3750 and 2970 Switches Using Switches with a PS Series Group Abstract This Technical Report describes how to use Cisco Catalyst 3750 and 2970 switches with a PS Series group to create a
More informationStorage Networking Strategy for the Next Five Years
White Paper Storage Networking Strategy for the Next Five Years 2018 Cisco and/or its affiliates. All rights reserved. This document is Cisco Public Information. Page 1 of 8 Top considerations for storage
More informationScalability Considerations
CHAPTER 3 This chapter presents the steps to selecting products for a VPN solution, starting with sizing the headend, and then choosing products that can be deployed for headend devices. This chapter concludes
More informationChapter 1: Enterprise Campus Architecture. Course v6 Chapter # , Cisco Systems, Inc. All rights reserved. Cisco Public
Chapter 1: Analyzing The Cisco Enterprise Campus Architecture CCNP SWITCH: Implementing IP Switching Course v6 1 Chapter 1 Objectives Describe common campus design options and how design choices affect
More informationRoCE vs. iwarp Competitive Analysis
WHITE PAPER February 217 RoCE vs. iwarp Competitive Analysis Executive Summary...1 RoCE s Advantages over iwarp...1 Performance and Benchmark Examples...3 Best Performance for Virtualization...5 Summary...6
More informationA Low Latency Solution Stack for High Frequency Trading. High-Frequency Trading. Solution. White Paper
A Low Latency Solution Stack for High Frequency Trading White Paper High-Frequency Trading High-frequency trading has gained a strong foothold in financial markets, driven by several factors including
More informationCisco UCS Virtual Interface Card 1225
Data Sheet Cisco UCS Virtual Interface Card 1225 Cisco Unified Computing System Overview The Cisco Unified Computing System (Cisco UCS ) is a next-generation data center platform that unites compute, networking,
More informationIBM WebSphere MQ Low Latency Messaging Software Tested With Arista 10 Gigabit Ethernet Switch and Mellanox ConnectX
IBM WebSphere MQ Low Latency Messaging Software Tested With Arista 10 Gigabit Ethernet Switch and Mellanox ConnectX -2 EN with RoCE Adapter Delivers Reliable Multicast Messaging With Ultra Low Latency
More informationVirtuozzo Hyperconverged Platform Uses Intel Optane SSDs to Accelerate Performance for Containers and VMs
Solution brief Software-Defined Data Center (SDDC) Hyperconverged Platforms Virtuozzo Hyperconverged Platform Uses Intel Optane SSDs to Accelerate Performance for Containers and VMs Virtuozzo benchmark
More informationGUIDE. Optimal Network Designs with Cohesity
Optimal Network Designs with Cohesity TABLE OF CONTENTS Introduction...3 Key Concepts...4 Five Common Configurations...5 3.1 Simple Topology...5 3.2 Standard Topology...6 3.3 Layered Topology...7 3.4 Cisco
More informationvsan 6.6 Performance Improvements First Published On: Last Updated On:
vsan 6.6 Performance Improvements First Published On: 07-24-2017 Last Updated On: 07-28-2017 1 Table of Contents 1. Overview 1.1.Executive Summary 1.2.Introduction 2. vsan Testing Configuration and Conditions
More informationSAP High-Performance Analytic Appliance on the Cisco Unified Computing System
Solution Overview SAP High-Performance Analytic Appliance on the Cisco Unified Computing System What You Will Learn The SAP High-Performance Analytic Appliance (HANA) is a new non-intrusive hardware and
More informationDiffusion TM 5.0 Performance Benchmarks
Diffusion TM 5.0 Performance Benchmarks Contents Introduction 3 Benchmark Overview 3 Methodology 4 Results 5 Conclusion 7 Appendix A Environment 8 Diffusion TM 5.0 Performance Benchmarks 2 1 Introduction
More informationCisco Nexus 9508 Switch Power and Performance
White Paper Cisco Nexus 9508 Switch Power and Performance The Cisco Nexus 9508 brings together data center switching power efficiency and forwarding performance in a high-density 40 Gigabit Ethernet form
More informationThe Network Layer and Routers
The Network Layer and Routers Daniel Zappala CS 460 Computer Networking Brigham Young University 2/18 Network Layer deliver packets from sending host to receiving host must be on every host, router in
More informationINSIGHTS. FPGA - Beyond Market Data. Financial Markets
FPGA - Beyond Market In this article, Mike O Hara, publisher of The Trading Mesh - talks to Mike Schonberg of Quincy, Laurent de Barry and Nicolas Karonis of Enyx and Henry Young of TS-Associates, about
More informationCisco 4000 Series Integrated Services Routers: Architecture for Branch-Office Agility
White Paper Cisco 4000 Series Integrated Services Routers: Architecture for Branch-Office Agility The Cisco 4000 Series Integrated Services Routers (ISRs) are designed for distributed organizations with
More informationMessaging Overview. Introduction. Gen-Z Messaging
Page 1 of 6 Messaging Overview Introduction Gen-Z is a new data access technology that not only enhances memory and data storage solutions, but also provides a framework for both optimized and traditional
More informationSolace s Unified Messaging Platform
Over the years most enterprises have bought and built many different messaging systems to serve as the infrastructure for their distributed applications. Most of these have been based on messaging software
More informationExam Code: Exam Code: Exam Name: Advanced Borderless Network Architecture Systems Engineer test.
Exam Code: 700-303 Number: 700-303 Passing Score: 800 Time Limit: 120 min File Version: 41.2 http://www.gratisexam.com/ Exam Code: 700-303 Exam Name: Advanced Borderless Network Architecture Systems Engineer
More informationSEVONE DATA APPLIANCE FOR EUE
Insight for the Connected World Data Appliance for EUE [ DataSheet ] SEVONE DATA APPLIANCE FOR EUE INSIGHTS FROM THE USER PERSPECTIVE. Software, applications and services running on the network infrastructure
More information6 Key Factors to Consider When Choosing a Transparent Caching Solution
6 Key Factors to Consider When Choosing a Transparent Caching Solution 2013 Qwilt 1 OVERVIEW Transparent caching solutions help carriers reduce the impact of over-the-top (OTT) video traffic on their networks,
More informationArchitecting the High Performance Storage Network
Architecting the High Performance Storage Network Jim Metzler Ashton, Metzler & Associates Table of Contents 1.0 Executive Summary...3 3.0 SAN Architectural Principals...5 4.0 The Current Best Practices
More informationLossless 10 Gigabit Ethernet: The Unifying Infrastructure for SAN and LAN Consolidation
. White Paper Lossless 10 Gigabit Ethernet: The Unifying Infrastructure for SAN and LAN Consolidation Introduction As organizations increasingly rely on IT to help enable, and even change, their business
More informationCisco Nexus 5000 and Emulex LP21000
Cisco Nexus 5000 and Emulex LP21000 A Fibre Channel over Ethernet Technology and Solutions Overview Prepared by: Cisco Systems, Inc. and Emulex Introduction Data center managers today are being challenged
More informationSEVONE END USER EXPERIENCE
Insight for the Connected World End User Experience [ DataSheet ] SEVONE END USER EXPERIENCE INSIGHTS FROM THE USER PERSPECTIVE. Software, applications and services running on the network infrastructure
More informationUpgrade Your MuleESB with Solace s Messaging Infrastructure
The era of ubiquitous connectivity is upon us. The amount of data most modern enterprises must collect, process and distribute is exploding as a result of real-time process flows, big data, ubiquitous
More informationDeploy a High-Performance Database Solution: Cisco UCS B420 M4 Blade Server with Fusion iomemory PX600 Using Oracle Database 12c
White Paper Deploy a High-Performance Database Solution: Cisco UCS B420 M4 Blade Server with Fusion iomemory PX600 Using Oracle Database 12c What You Will Learn This document demonstrates the benefits
More informationInterface The exit interface a packet will take when destined for a specific network.
The Network Layer The Network layer (also called layer 3) manages device addressing, tracks the location of devices on the network, and determines the best way to move data, which means that the Network
More informationReduces latency and buffer overhead. Messaging occurs at a speed close to the processors being directly connected. Less error detection
Switching Operational modes: Store-and-forward: Each switch receives an entire packet before it forwards it onto the next switch - useful in a general purpose network (I.e. a LAN). usually, there is a
More informationDDoS: STRATEGIES FOR DEALING WITH A GROWING THREAT
DDoS: STRATEGIES FOR DEALING WITH A GROWING THREAT 01. EXECUTIVE SUMMARY This report summarizes recent research on distributed denial of service (DDoS) attacks, which looks at data collated recently and
More informationThe Total Network Volume chart shows the total traffic volume for the group of elements in the report.
Tjänst: Network Health Total Network Volume and Total Call Volume Charts Public The Total Network Volume chart shows the total traffic volume for the group of elements in the report. Chart Description
More informationMaximize the All-Flash Data Center with Brocade Gen 6 Fibre Channel
WHITE PAPER Maximize the All-Flash Data Center with Brocade Gen 6 Fibre Channel Introduction The flash and hybrid takeover of the data center storage market has quickly gained momentum. In fact, the adoption
More informationSeven Criteria for a Sound Investment in WAN Optimization
Seven Criteria for a Sound Investment in WAN Optimization Introduction WAN optimization technology brings three important business benefits to IT organizations: Reduces branch office infrastructure costs
More informationCisco UCS Virtual Interface Card 1227
Data Sheet Cisco UCS Virtual Interface Card 1227 Cisco Unified Computing System Overview The Cisco Unified Computing System (Cisco UCS ) is a next-generation data center platform that unites computing,
More informationFinancial Services Design for High Availability
Financial Services Design for High Availability Version History Version Number Date Notes 1 March 28, 2003 This document was created. This document describes the best practice for building a multicast
More informationBenefits of SDN Modeling and Analytics tool for complex Service Provider Network
Benefits of SDN Modeling and Analytics tool for complex Service Provider Network George Backer, Senior Director, Charter Communications Manish Jani, Senior Architect, Cisco Systems BRKNMS-1010 BRKNMS-1010
More informationUse of the Internet SCSI (iscsi) protocol
A unified networking approach to iscsi storage with Broadcom controllers By Dhiraj Sehgal, Abhijit Aswath, and Srinivas Thodati In environments based on Internet SCSI (iscsi) and 10 Gigabit Ethernet, deploying
More informationDeploying Gigabit Ethernet to the Desktop: Drivers and Applications
Deploying Gigabit Ethernet to the Desktop: Drivers and Applications The Federal Reserve estimates that the greater use of information technology accounts for 60 percent of the gains in the non-farm business
More informationOptimize and Accelerate Your Mission- Critical Applications across the WAN
BIG IP WAN Optimization Module DATASHEET What s Inside: 1 Key Benefits 2 BIG-IP WAN Optimization Infrastructure 3 Data Optimization Across the WAN 4 TCP Optimization 4 Application Protocol Optimization
More informationThe Why, What, and How of Cisco Tetration
The Why, What, and How of Cisco Tetration Why Cisco Tetration? With the above trends as a backdrop, Cisco has seen specific changes within the multicloud data center. Infrastructure is changing. It is
More informationMellanox InfiniBand Solutions Accelerate Oracle s Data Center and Cloud Solutions
Mellanox InfiniBand Solutions Accelerate Oracle s Data Center and Cloud Solutions Providing Superior Server and Storage Performance, Efficiency and Return on Investment As Announced and Demonstrated at
More informationIntel Network Builders Solution Brief. Etisalat* and Intel Virtualizing the Internet. Flexibility
Intel Network Builders Solution Brief Etisalat* and Intel Virtualizing the Internet Gateway Gi-LAN for Service Flexibility Introduction Etisalat Group* is one of the world s leading telecom groups in emerging
More informationVisual TruView Unified Network and Application Performance Management Focused on the Experience of the End User
Visual TruView Unified Network and Application Performance Management Focused on the Experience of the End User BUSINESS CHALLENGE Problems can occur anywhere from the physical layer to wireless, across
More informationInfiniBand SDR, DDR, and QDR Technology Guide
White Paper InfiniBand SDR, DDR, and QDR Technology Guide The InfiniBand standard supports single, double, and quadruple data rate that enables an InfiniBand link to transmit more data. This paper discusses
More informationChanging the Economics of Lossless Full Packet Capture Enabling Real-time Visibility
Executive Summary: Changing the Economics of Lossless Full Packet Capture Enabling Real-time Visibility March 2017 All questions and enquiries regarding this white paper should be directed to: Dan Cybulski
More informationEMC Celerra Replicator V2 with Silver Peak WAN Optimization
EMC Celerra Replicator V2 with Silver Peak WAN Optimization Applied Technology Abstract This white paper discusses the interoperability and performance of EMC Celerra Replicator V2 with Silver Peak s WAN
More information10 Steps to Virtualization
AN INTEL COMPANY 10 Steps to Virtualization WHEN IT MATTERS, IT RUNS ON WIND RIVER EXECUTIVE SUMMARY Virtualization the creation of multiple virtual machines (VMs) on a single piece of hardware, where
More informationWebSphere MQ Low Latency Messaging V2.1. High Throughput and Low Latency to Maximize Business Responsiveness IBM Corporation
WebSphere MQ Low Latency Messaging V2.1 High Throughput and Low Latency to Maximize Business Responsiveness 2008 IBM Corporation WebSphere MQ Low Latency Messaging Extends the WebSphere MQ messaging family
More informationCisco Nexus 4000 Series Switches for IBM BladeCenter
Cisco Nexus 4000 Series Switches for IBM BladeCenter What You Will Learn This document is targeted at server, storage, and network administrators planning to deploy IBM BladeCenter servers with the unified
More informationINTERNATIONAL LAW ENFORCEMENT HD CCTV NETWORK
INTERNATIONAL LAW ENFORCEMENT HD CCTV NETWORK CASE STUDY Application of High-Assurance Network Encryption Sector: Use Case: Solution: Government CCTV security Real-time HD video transmission across Layer
More informationLoad Dynamix Enterprise 5.2
DATASHEET Load Dynamix Enterprise 5.2 Storage performance analytics for comprehensive workload insight Load DynamiX Enterprise software is the industry s only automated workload acquisition, workload analysis,
More informationDrive Greater Value from Your Cisco Deployment with Radware Solutions
Drive Greater Value from Your Cisco Deployment with Radware Solutions Ron Meyran Director, Alliances Marketing Feb 24, 2015 Introducing Radware Radware/Cisco Solution Mapping Solutions Overview & Differentiators
More informationINT G bit TCP Offload Engine SOC
INT 10011 10 G bit TCP Offload Engine SOC Product brief, features and benefits summary: Highly customizable hardware IP block. Easily portable to ASIC flow, Xilinx/Altera FPGAs or Structured ASIC flow.
More informationAccelerate Your Enterprise Private Cloud Initiative
Cisco Cloud Comprehensive, enterprise cloud enablement services help you realize a secure, agile, and highly automated infrastructure-as-a-service (IaaS) environment for cost-effective, rapid IT service
More informationCampus Network Design
Modular Network Design Campus Network Design Modules are analogous to building blocks of different shapes and sizes; when creating a building, each block has different functions Designing one of these
More informationTechnical Document. What You Need to Know About Ethernet Audio
Technical Document What You Need to Know About Ethernet Audio Overview Designing and implementing an IP-Audio Network can be a daunting task. The purpose of this paper is to help make some of these decisions
More informationLOW LATENCY DATA DISTRIBUTION IN CAPITAL MARKETS: GETTING IT RIGHT
LOW LATENCY DATA DISTRIBUTION IN CAPITAL MARKETS: GETTING IT RIGHT PATRICK KUSTER Head of Business Development, Enterprise Capabilities, Thomson Reuters +358 (40) 840 7788; patrick.kuster@thomsonreuters.com
More information10Gb Ethernet: The Foundation for Low-Latency, Real-Time Financial Services Applications and Other, Latency-Sensitive Applications
10Gb Ethernet: The Foundation for Low-Latency, Real-Time Financial Services Applications and Other, Latency-Sensitive Applications Testing conducted by Solarflare and Arista Networks reveals single-digit
More informationTop 5 Reasons to Consider
Top 5 Reasons to Consider NVM Express over Fabrics For Your Cloud Data Center White Paper Top 5 Reasons to Consider NVM Express over Fabrics For Your Cloud Data Center Major transformations are occurring
More informationUse Cases for iscsi and FCoE: Where Each Makes Sense
Use Cases for iscsi and FCoE: Where Each Makes Sense PRESENTATION TITLE GOES HERE February 18, 2014 Today s Presenters David Fair, SNIA ESF Business Development Chair - Intel Sameh Boujelbene - Director,
More informationAMD Opteron Processors In the Cloud
AMD Opteron Processors In the Cloud Pat Patla Vice President Product Marketing AMD DID YOU KNOW? By 2020, every byte of data will pass through the cloud *Source IDC 2 AMD Opteron In The Cloud October,
More informationRack-Level I/O Consolidation with Cisco Nexus 5000 Series Switches
. White Paper Rack-Level I/O Consolidation with Cisco Nexus 5000 Series Switches Introduction Best practices for I/O connectivity in today s data centers configure each server with redundant connections
More informationIntroduction to Cisco ASR 9000 Series Network Virtualization Technology
White Paper Introduction to Cisco ASR 9000 Series Network Virtualization Technology What You Will Learn Service providers worldwide face high customer expectations along with growing demand for network
More informationWHITE PAPER: PROFISHARK PERFORMANCE RESULTS WIRESHARK HEROES SERIES VISIT
WHITE PAPER: PROFISHARK PERFORMANCE WIRESHARK HEROES SERIES VISIT WWW.PROFITAP.COM TABLE OF CONTENT TONY FORTUNATO NETWORK PERFORMANCE SPECIALIST Tony Fortunato is a Senior Network Performance Specialist
More informationQuickSpecs. HP Z 10GbE Dual Port Module. Models
Overview Models Part Number: 1Ql49AA Introduction The is a 10GBASE-T adapter utilizing the Intel X722 MAC and X557-AT2 PHY pairing to deliver full line-rate performance, utilizing CAT 6A UTP cabling (or
More informationCisco SCE 2020 Service Control Engine
Data Sheet Cisco SCE 2000 Series Service Control Engine The Cisco SCE 2000 Series Service Control Engine is a network element specifically designed for carrier-grade deployments requiring high-capacity
More informationElevate the Branch-Office Experience with an Application-Centric Platform
White Paper Elevate the Branch-Office Experience with an Application-Centric Platform Today s branch office requires the same level of rich application services as the company headquarters to ensure business
More informationCisco UCS Mini Software-Defined Storage with StorMagic SvSAN for Remote Offices
Solution Overview Cisco UCS Mini Software-Defined Storage with StorMagic SvSAN for Remote Offices BENEFITS Cisco UCS and StorMagic SvSAN deliver a solution to the edge: Single addressable storage pool
More informationSOLUTION BRIEF Enterprise WAN Agility, Simplicity and Performance with Software-Defined WAN
S O L U T I O N O V E R V I E W SOLUTION BRIEF Enterprise WAN Agility, Simplicity and Performance with Software-Defined WAN Today s branch office users are consuming more wide area network (WAN) bandwidth
More informationFive Reasons Why You Should Choose Cisco MDS 9000 Family Directors Cisco and/or its affiliates. All rights reserved.
Five Reasons Why You Should Choose Cisco MDS 9000 Family Directors 2017 Cisco and/or its affiliates. All rights reserved. Contents Overview... 2 1. Integrated Analytics for Deep Visibility...3 2. Performance
More informationChapter 10: Planning and Cabling Networks
Chapter 10: Planning and Cabling Networks Before using an IP phone, accessing instant messaging, or conducting any number of other interactions over a data network, we must connect end devices and intermediary
More informationOptimizing Pulse Secure Access Suite with Pulse Secure Virtual Application Delivery Controller solution
DATASHEET Optimizing Pulse Secure Access Suite with Pulse Secure Virtual Application Delivery Controller solution Features & Benefits Best-in-class VPN and vadc solutions A single point of access for all
More informationFeatures. HDX WAN optimization. QoS
May 2013 Citrix CloudBridge Accelerates, controls and optimizes applications to all locations: datacenter, branch offices, public and private clouds and mobile users Citrix CloudBridge provides a unified
More informationLAN Based Radio Synchronization
LAN Based Radio Synchronization Introduction The latest generation of Spectralink IP-DECT base stations supports to use Local Area Network (LAN) for synchronization of the DECT radios when running software
More informationINTRODUCTORY Q&A AMX SVSI NETWORKED AV
INTRODUCTORY Q&A AMX SVSI NETWORKED AV WE KNOW YOU HAVE QUESTIONS As an IT professional, it is your job to make sure that any application being deployed on the network is safe and secure. But we know that
More informationEvaluate Data Center Network Performance
Downloaded from orbit.dtu.dk on: Sep 02, 2018 Evaluate Data Center Network Performance Pilimon, Artur Publication date: 2018 Document Version Publisher's PDF, also known as Version of record Link back
More informationCisco HyperFlex Systems
White Paper Cisco HyperFlex Systems Install and Manage Cisco HyperFlex Systems in a Cisco ACI Environment Original Update: January 2017 Updated: March 2018 Note: This document contains material and data
More informationWhite paper. Keys to Oracle application acceleration: advances in delivery systems.
White paper Keys to Oracle application acceleration: advances in delivery systems. Table of contents The challenges of fast Oracle application delivery...3 Solving the acceleration challenge: why traditional
More informationHP BladeSystem c-class Ethernet network adapters
HP BladeSystem c-class Ethernet network adapters Family data sheet HP NC552m 10 Gb Dual Port Flex-10 Ethernet Adapter HP NC551m Dual Port FlexFabric 10 Gb Converged Network Adapter HP NC550m 10 Gb Dual
More informationSend documentation comments to You must enable FCIP before attempting to configure it on the switch.
CHAPTER 9 (Fibre Channel over IP) is an IETF standards based protocol for connecting Fibre Channel SANs over IP based networks. encapsulates the FCP frames in a TCP/IP packet which is then sent across
More informationVXLAN Overview: Cisco Nexus 9000 Series Switches
White Paper VXLAN Overview: Cisco Nexus 9000 Series Switches What You Will Learn Traditional network segmentation has been provided by VLANs that are standardized under the IEEE 802.1Q group. VLANs provide
More informationThe Next Opportunity in the Data Centre
The Next Opportunity in the Data Centre Application Centric Infrastructure Soni Jiandani Senior Vice President, Cisco THE NETWORK IS THE INFORMATION BROKER FOR ALL APPLICATIONS Applications Are Changing
More informationIntroduction to iscsi
Introduction to iscsi As Ethernet begins to enter into the Storage world a new protocol has been getting a lot of attention. The Internet Small Computer Systems Interface or iscsi, is an end-to-end protocol
More informationHP BladeSystem c-class Ethernet network adaptors
HP BladeSystem c-class Ethernet network adaptors Family data sheet NC325m Quad-port Gigabit NC326m Dual-port Gigabit NC360m Dual-port Gigabit NC364m Quad-port Gigabit NC382m Dual-port Multifunction Gigabit
More informationMigrate from Cisco Catalyst 6500 Series Switches to Cisco Nexus 9000 Series Switches
Migration Guide Migrate from Cisco Catalyst 6500 Series Switches to Cisco Nexus 9000 Series Switches Migration Guide November 2013 2013 Cisco and/or its affiliates. All rights reserved. This document is
More informationCampus Network Design. 2003, Cisco Systems, Inc. All rights reserved. 2-1
Campus Network Design 2003, Cisco Systems, Inc. All rights reserved. 2-1 Design Objective Business Requirement Why do you want to build a network? Too often people build networks based on technological,
More information